Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

AI-901 Azure AI Fundamentals | Azure Certification

Name: AI-901 Azure AI Fundamentals | Azure Certification
Rating: 4.4 (1124 reviews)

AI 901 | Microsoft Azure AI Fundamentals (Updated from AI-900) | Exam Prep with Microsoft Foundry

Role Play

Created byPraveenkumar Bouna

Last updated 8/2026

English

EnglishFrench [Auto],

What you'll learn

AI fundamentals and responsible AI
AI model components, types, and configuration
AI workloads: text analysis, speech, computer vision, information extraction
Generative AI apps and agents with Microsoft Foundry
Text analysis and speech implementation with Foundry Tools
Computer vision and image generation with Foundry
Information extraction with Azure Content Understanding
AI-901 (formerly AI-900) exam preparation and practice tests

Course content

10 sections • 79 lectures • 3h 43m total length

Overview of AI-901 exam3:08
After this lecture, you will be able to describe the AI-901 exam format, scoring, prerequisites, and who the certification is for.
AI-901 skills measured2:01
After this lecture, you will be able to explain the two AI-901 exam domains, their weightings, and the skills measured in each.
Helpful resources for exam preparation1:53
After this lecture, you will be able to locate and use official Microsoft resources to prepare for the AI-901 exam.
Activity: Review the Official Study Guide for AI-9010:07
After this lecture, you will be able to know the current syllabus for the AI-901 exam from the official Microsoft website.
How much time will AI-901 exam prep take?1:29
After this lecture, you will be able to estimate a realistic study timeline based on your background and experience level.
Join the Discord community0:11
After this lecture, you will be able to connect with other AI-901 learners through the course Discord community for support and study groups.
Overview of AI2:56
After this lecture, you will be able to explain what artificial intelligence is, how AI applications differ from models, and the major AI workloads covered in the course.
Demo: Creating an Azure account2:01
After this lecture, you will be able to create a free Azure account through the Azure portal to support hands-on practice in the course.
Create your free Azure account0:46
After this lecture, you will be able to understand the benefits, free-tier offerings, and sign-up steps for a new Azure account.
Course code samples on GitHub0:18
After this lecture, you will be able to locate and run the demo code samples used throughout this course from the official GitHub repository.

Overview of Responsible AI2:01
After this lecture, you will be able to define Responsible AI and describe Microsoft's six guiding principles for building trustworthy AI systems.
Principle 1: Fairness1:52
After this lecture, you will be able to explain the fairness principle and identify scenarios where AI systems may produce biased outcomes.
Principle 2: Reliability and safety1:39
After this lecture, you will be able to explain the reliability and safety principle and recognize when human oversight is needed for AI decisions.
Principle 3: Privacy and security1:40
After this lecture, you will be able to explain how the privacy and security principle applies to data collection, protection, and retention in AI systems.
Principle 4: Inclusiveness1:38
After this lecture, you will be able to explain the inclusiveness principle and design considerations that make AI systems accessible to diverse users.
Principle 5: Transparency1:30
After this lecture, you will be able to explain the transparency principle and when AI systems should disclose their capabilities and limitations to users.
Principle 6: Accountability1:52
After this lecture, you will be able to explain the accountability principle and the governance practices needed for responsible AI deployment.
Demo: Guiding principles for Responsible AI1:42
After this lecture, you will be able to navigate Microsoft's Responsible AI resources and review the goals defined for each principle.
Exam tips: Responsible AI2:27
After this lecture, you will be able to apply keyword clues and a quick-reference map to answer Responsible AI scenario questions on the exam.
Principles of Responsible AI
Implementing Responsible AI in Healthcare Analytics

Generative AI concepts and LLMs3:08
After this lecture, you will be able to explain how generative AI and large language models work, including tokens, embeddings, and key capabilities and limitations.
Design patterns for generative AI applications2:18
After this lecture, you will be able to describe common generative AI design patterns including prompt engineering, RAG, fine-tuning, and agentic workflows.
AI models: Types, selection, and configuration3:40
After this lecture, you will be able to compare model types in the Foundry catalog and select the right model for a given task.
Demo: Exploring the Microsoft Foundry portal3:51
After this lecture, you will be able to create a Foundry resource and navigate the portal's Discover, Build, and Operate areas.
Demo: AI Models in Microsoft Foundry3:20
After this lecture, you will be able to browse and filter models in the Foundry catalog by provider, task type, and fine-tuning support.
Model deployment options2:57
After this lecture, you will be able to compare Foundry deployment types and choose the right option based on data residency, traffic patterns, and latency needs.
Demo: Deployment types in Microsoft Foundry2:19
After this lecture, you will be able to review official documentation on Foundry deployment types and their data processing locations.
Model deployment configurations4:42
After this lecture, you will be able to configure deployment parameters such as temperature, top-p, and rate limits, and identify the correct API endpoints for Foundry services.
Exam tips: AI models and components2:44
After this lecture, you will be able to use a structured approach to match exam scenarios to the correct model, deployment type, and Foundry service.
AI model components and configurations

AI workloads overview3:04
After this lecture, you will be able to describe the six major AI workloads and compare their inputs, outputs, and example use cases.
Demo: AI workloads in Microsoft Azure2:59
After this lecture, you will be able to locate Microsoft Foundry workload documentation and identify the most exam-relevant resources.
Text analysis techniques2:53
After this lecture, you will be able to explain common text analysis techniques including language detection, entity recognition, sentiment analysis, and summarization.
Demo: Overview of Azure Language in Foundry1:38
After this lecture, you will be able to locate Azure Language capabilities in the Foundry portal, including detection, redaction, and translation features.
Speech capabilities2:27
After this lecture, you will be able to explain speech recognition, synthesis, and translation capabilities and how they work at a high level.
Demo: Overview of Azure Speech in Foundry2:36
After this lecture, you will be able to locate Azure Speech services in the Foundry portal and review configuration options for speech-to-text, text-to-speech, and translation.
Computer vision capabilities2:36
After this lecture, you will be able to explain core computer vision capabilities including classification, object detection, OCR, and multimodal analysis.
Information extraction capabilities2:52
After this lecture, you will be able to explain how information extraction combines OCR and AI to produce structured data from unstructured sources.
Demo: Overview of Content Understanding in Foundry1:25
After this lecture, you will be able to locate Content Understanding services in the Foundry portal and review available document extraction capabilities.
Generative AI capabilities1:46
After this lecture, you will be able to distinguish generative AI workloads from agentic AI workloads and describe what each produces.
Demo: Overview of Generative AI in Foundry2:06
After this lecture, you will be able to navigate Foundry's model catalog, agent templates, and deployment options for generative and agentic AI.
Exam tips: AI workloads3:20
After this lecture, you will be able to match exam scenarios to the correct AI workload and Foundry service using input-type and output-type clues.
AI Workloads

Introduction to Microsoft Foundry4:41
After this lecture, you will be able to describe Microsoft Foundry's four pillars, security model, and how it unifies models, agents, tools, and knowledge.
Demo: Deploying models in Foundry2:40
After this lecture, you will be able to deploy a model in Foundry, test it in the playground, and review its endpoint and deployment settings.
Prompt engineering3:36
After this lecture, you will be able to craft effective prompts using role, task, context, and format components to improve model responses.
Demo: Prompt engineering in Foundry3:01
After this lecture, you will be able to compare unstructured and engineered prompts in the Foundry playground and observe differences in response quality.
Microsoft Foundry SDK3:01
After this lecture, you will be able to identify the Foundry SDK packages, endpoint formats, and authentication patterns for calling models and agents.
Demo: Building a chat app with Foundry SDK3:41
After this lecture, you will be able to build a minimal Python chat application that calls a deployed model using the Foundry SDK.
Agentic AI4:47
After this lecture, you will be able to explain what AI agents are, their core components, and the difference between building and coding agents in Foundry.
Demo: Creating and testing an agent in Foundry3:24
After this lecture, you will be able to create an agent in the Foundry portal, attach a knowledge base, and test it in the agent playground.
Demo: Building a lightweight agent client app3:41
After this lecture, you will be able to build a Python client application that connects to a Foundry agent and handles multi-turn conversation.
Exam tips: Generative AI apps and agents in Foundry3:13
After this lecture, you will be able to distinguish model-only tasks from agentic scenarios and select the correct SDK, endpoint, and auth pattern on the exam.
Generative AI apps and agents using Microsoft Foundry

Natural Language Processing (NLP) capabilities and use cases6:19
After this lecture, you will be able to describe NLP capabilities including language detection, summarization, entity recognition, sentiment analysis, and speech processing.
Text analysis in Microsoft Foundry3:00
After this lecture, you will be able to compare general-purpose model analysis with Azure Language's deterministic analyzers and explain when to use each approach.
Demo: Text analysis via Microsoft Foundry tools3:08
After this lecture, you will be able to use Azure Language tools in the Foundry portal for language detection, PII redaction, and text translation.
Demo: Building a lightweight text analysis app5:39
After this lecture, you will be able to build a Python application that performs language detection, PII redaction, and sentiment analysis using the Azure Language SDK.
Azure Speech via Microsoft Foundry tools3:30
After this lecture, you will be able to describe Azure Speech capabilities including speech-to-text, text-to-speech, speech translation, and Voice Live.
Demo: Speech via Microsoft Foundry tools4:12
After this lecture, you will be able to use Azure Speech tools in the Foundry portal for transcription, synthesis, and speech translation.
Demo: Building a lightweight speech app4:05
After this lecture, you will be able to build a Python application that transcribes spoken input and synthesizes spoken responses using the Azure Speech SDK.
Demo: Using Azure Speech Voice Live4:02
After this lecture, you will be able to enable and test Voice Live on a Foundry agent for real-time conversational speech interactions.
Exam tips: Text analysis and speech4:05
After this lecture, you will be able to select the correct text or speech service for exam scenarios based on input type and output requirements.
Text Analysis and Speech Using Microsoft Foundry
Implementing NLP Solutions for Customer Service Enhancement

Features of computer vision3:32
After this lecture, you will be able to describe core computer vision capabilities and explain how generative AI is changing the vision landscape.
Image analysis in Microsoft Foundry2:39
After this lecture, you will be able to explain how multimodal models in Foundry analyze images through natural-language prompts.
Demo: Image analysis in Microsoft Foundry3:27
After this lecture, you will be able to upload images to the Foundry playground and use prompts to analyze visual content with a multimodal model.
Demo: Image analysis using Python SDK3:38
After this lecture, you will be able to build a Python application that sends images to a multimodal model via the Foundry SDK for visual analysis.
Image generation with generative models3:22
After this lecture, you will be able to explain how image generation models work and describe generation, editing, and variation capabilities.
Demo: Image generation in Microsoft Foundry3:50
After this lecture, you will be able to deploy a GPT-Image model and generate images from text prompts in the Foundry playground.
Demo: Image generation via Python SDK3:37
After this lecture, you will be able to call a GPT-Image deployment from Python using the Foundry SDK and Responses API.
Video generation with generative models3:52
After this lecture, you will be able to explain how Sora video generation works, its capabilities, and the async job pattern for creating videos.
Demo: Video generation in Microsoft Foundry2:58
After this lecture, you will be able to deploy a Sora model and generate video clips from text prompts in the Foundry playground.
Exam tips: Computer vision and image generation2:57
After this lecture, you will be able to distinguish computer vision analysis from image and video generation and identify the correct models for exam scenarios.
Computer Vision and Image Generation Using Microsoft Foundry

Information extraction overview2:06
After this lecture, you will be able to explain what information extraction is, its key benefits, and how Content Understanding extends document intelligence.
Extraction from documents, images, audio, and video2:51
After this lecture, you will be able to describe how structured data is extracted from different content types and how confidence scores guide processing decisions.
Azure Content Understanding4:02
After this lecture, you will be able to explain how Azure Content Understanding works, including its schema-based extraction workflow and key components.
Demo: Content Understanding in Microsoft Foundry3:09
After this lecture, you will be able to use Content Understanding in the Foundry portal to extract text, layout, and fields from documents and audio.
Content Understanding analyzers — prebuilt and custom2:16
After this lecture, you will be able to distinguish prebuilt Content Understanding analyzers from custom analyzers and identify the correct analyzer for a scenario.
Demo: Building a lightweight information extraction app3:36
After this lecture, you will be able to build a Python application that extracts structured data from content using Azure Content Understanding.
Exam tips: Information extraction and Content Understanding3:10
After this lecture, you will be able to select the correct extraction service and analyzer for exam scenarios based on content type and output requirements.
Information Extraction Using Microsoft Foundry

Exam tips: Preparing for AI-901 exam2:32
After this lecture, you will be able to plan your final exam preparation, choose between in-person and online proctoring, and prepare your environment for exam day.
Next steps after passing AI-901 exam1:35
After this lecture, you will be able to identify recommended next certifications and steps to advance your Azure AI career after passing AI-901.
What's Next — Strengthen Your Azure Foundation0:30
After this lecture, you will be able to explain why foundational Azure knowledge strengthens your AI skills and identify the AZ-900 certification path as a recommended next step after AI-901.

Requirements

Learners should have basic familiarity with Python syntax and programming concepts.
Basic familiarity with the Azure portal and Azure resources is helpful but not required.
No prior AI or machine learning experience is needed. An Azure account (free trial is sufficient) is required to follow along with the demos.

Description

Empower your team for the AI-901 Microsoft Azure AI Fundamentals certification — hands-on exam prep with Microsoft Foundry that replaces AI-900.

The AI-901 exam demands both conceptual depth and practical implementation — a significant step beyond AI-900. This course equips your team with responsible AI principles, Azure AI workload knowledge, and hands-on Foundry experience building generative AI apps, agents, and solutions across text, speech, vision, and document extraction. Team members finish prepared to pass the AI 901 exam and apply certified skills to build, deploy, and govern AI on Azure.

Business Impact:

Enable your team to make informed decisions about AI adoption, model selection, and Azure AI service evaluation.
Equip developers and professionals with the skills to begin implementing AI solutions using Microsoft Foundry.
Improve AI literacy across roles, from implementation to governance and responsible AI practices.
Accelerate your organization's AI transformation with certified, hands-on skills.
Reduce risk through a team that understands responsible AI principles, safety guardrails, and compliance considerations.

Instructor Expertise:

Praveen brings 18+ years of enterprise experience from Honeywell and Bosch, specializing in cloud-native and AI technologies. His credentials include a patent, published research papers, and a track record of training thousands of professionals through 30+ courses and 70+ hands-on labs. Praveen will guide your team through every concept and implementation needed to pass the AI-901 exam (formerly known as AI-900) and build real AI solutions.

Comprehensive Curriculum:

AI fundamentals and responsible AI
AI model components, types, and configuration
AI workloads: text analysis, speech, computer vision, information extraction
Generative AI apps and agents with Microsoft Foundry
Text analysis and speech implementation with Foundry Tools
Computer vision and image generation with Foundry
Information extraction with Azure Content Understanding
AI-901 (formerly AI-900) exam preparation and practice tests

ROI for Your Organization:

Standardize AI knowledge and implementation skills across team members.
Verified skill development through the Microsoft Certified: Azure AI Fundamentals certification.
Equip your team to build production-ready AI solutions using Microsoft Foundry.
Reduce training costs with a comprehensive, exam-aligned course.

Perfect for teams:

Building or evaluating AI-powered applications on Azure.
Needing foundational AI knowledge before tackling advanced AI roles.
Working on digital transformation and AI adoption initiatives.
Requiring AI certification for compliance or role advancement.

By the end of this course:

Your team will understand core AI concepts, responsible AI principles, and the full range of Azure AI workloads.
Your team members will be prepared to pass the AI-901 exam and earn the Microsoft Certified: Azure AI Fundamentals certification.
Your developers will be able to begin implementing AI solutions using Microsoft Foundry — covering generative AI, agents, text, speech, vision, and information extraction.

Enroll now or assign to your team to start the journey toward AI certification and real-world AI implementation on Azure.

Who this course is for:

Developers, IT professionals, data professionals, and technology workers preparing for the AI-901 certification.
Teams looking to establish foundational AI skills and implement AI solutions using Microsoft Foundry.
Anyone who wants hands-on experience building AI applications on Azure.

AI-901 Azure AI Fundamentals | Azure Certification

What you'll learn

Explore related topics

Course content

Getting started with AI-90110 lectures • 15min

AI-901: Principles of Responsible AI10 lectures • 16min

AI-901: AI model components and configurations9 lectures • 29min

AI-901: AI workloads12 lectures • 30min

AI-901: Generative AI apps and agents using Microsoft Foundry10 lectures • 36min

AI-901: Text analysis and speech using Microsoft Foundry10 lectures • 38min

AI-901: Computer vision and image generation using Microsoft Foundry10 lectures • 34min

AI-901: Information extraction using Microsoft Foundry7 lectures • 21min

AI-901: Practice tests0

What's next?3 lectures • 5min

Requirements

Description

Who this course is for: